Influence of extreme prematurity and bronchopulmonary dysplasia on cardiac function

Atrial septal defect closure is associated with improved clinical status in patients ≤ 10 kg with bronchopulmonary dysplasia

Patients with bronchopulmonary dysplasia (BPD) have shown clinical improvement after secundum atrial septal defect (ASD) closure. We sought to determine if this post-ASD closure improvement is secondary to the expected course in BPD patients or related to the closure itself. A novel BPD-ASD score was created to assess patients' clinical status (higher score = worse disease) and applied to 10 BPD-ASD inpatients weighing ≤ 10 kg who underwent ASD closure. The score and its subcomponents were retrospectively calculated serially ranging from 8 weeks pre- to 8 weeks post-intervention, and pre- and post-intervention score slopes were created. These slopes were compared using mixed regression modeling with an interaction term. There was a significant difference in pre- versus post-intervention slope with the most score drop the first week post-intervention (-2.1 + /- 0.8, p = 0.014). The mean score also dropped through weeks 2 (slope -0.8 + /- 0.8, p = 0.013) and 4 (slope -1.0 + /- 0.5, p = 0.001) post-intervention. There was a significant difference in pre- and post-intervention slopes for diuretics (p = 0.018) and the combined score of respiratory support, FiO2 need, and respiratory symptoms (p = 0.018). This study demonstrated significant improvement in BPD-ASD score, diuretic need, and respiratory status after ASD closure in BPD-ASD patients ≤ 10 kg that was outside of the natural course of BPD. Our study was limited by its small, single-center, retrospective nature. Future studies should be performed in a larger multicenter population to both validate the scoring system and compare to non-intervention infants.

A scoping review of echocardiographic and lung ultrasound biomarkers of bronchopulmonary dysplasia in preterm infants

Despite recent improvements in neonatal care, moderate to severe bronchopulmonary dysplasia (BPD) is still associated with high mortality and with an increased risk of developing pulmonary hypertension (PH). This scoping review provides an updated overview of echocardiographic and lung ultrasound biomarkers associated with BPD and PH, and the parameters that may prognosticate their development and severity, which could be clinically helpful to undertake preventive strategies. A literature search for published clinical studies was conducted in PubMed using MeSH terms, free-text words, and their combinations obtained through appropriate Boolean operators. It was found that the echocardiography biomarkers for BPD, and especially those assessing right ventricular function, are reflective of the high pulmonary vascular resistance and PH, indicating a strong interplay between heart and lung pathophysiology; however, early assessment (e.g., during the first 1-2 weeks of life) may not successfully predict later BPD development. Lung ultrasound indicating poor lung aeration at day 7 after birth has been reported to be highly predictive of later development of BPD at 36 weeks' postmenstrual age. Evidence of PH in BPD infants increases risk of mortality and long-term PH; hence, routine PH surveillance in all at risk preterm infants at 36 weeks, including an echocardiographic assessment, may provide useful information. Progress has been made in identifying the echocardiographic parameters on day 7 and 14 to predict later development of pulmonary hypertension. More studies on sonographic markers, and especially on echocardiographic parameters, are needed for the validation of the currently proposed parameters and the timing of assessment before recommendations can be made for the routine clinical practice.

Early severity prediction of BPD for premature infants from chest X-ray images using deep learning: A study at the 28th day of oxygen inhalation

BACKGROUND AND OBJECTIVE

Bronchopulmonary dysplasia is a common respiratory disease in premature infants. The severity is diagnosed at the 56th day after birth or discharge by analyzing the clinical indicators, which may cause the delay of the best treatment opportunity. Thus, we proposed a deep learning-based method using chest X-ray images of the 28th day of oxygen inhalation for the early severity prediction of bronchopulmonary dysplasia in clinic.

METHODS

We first adopted a two-step lung field extraction method by combining digital image processing and human-computer interaction to form the one-to-one corresponding image and label. The designed XSEG-Net model was then trained for segmenting the chest X-ray images, with the results being used for the analysis of heart development and clinical severity. Therein, Six-Point cardiothoracic ratio measurement algorithm based on corner detection was designed for the analysis of heart development; and the transfer learning of deep convolutional neural network models were used for the early prediction of clinical severities.

RESULTS

The dice and cross-entropy loss value of the training of XSEG-Net network reached 0.9794 and 0.0146. The dice, volumetric overlap error, relative volume difference, precision, and recall were used to evaluate the trained model in testing set with the result being 98.43 ± 0.39%, 0.49 ± 0.35%, 0.49 ± 0.35%, 98.67 ± 0.40%, and 98.20 ± 0.47%, respectively. The errors between the Six-Point cardiothoracic ratio measurement method and the gold standard were 0.0122 ± 0.0084. The deep convolutional neural network model based on VGGNet had the promising prediction performance, with the accuracy, precision, sensitivity, specificity, and F1 score reaching 95.58 ± 0.48%, 95.61 ± 0.55%, 95.67 ± 0.44%, 96.98 ± 0.42%, and 95.61±0.48%, respectively.

CONCLUSIONS

These experimental results of the proposed methods in lung field segmentation, cardiothoracic ratio measurement and clinic severity prediction were better than previous methods, which proved that this method had great potential for clinical application.